Plugins

Self-contained DeepSeek Harness (DSH) plugin for Provider/Auth login, model switching, image fallback, token/cost analytics, and same-port Web restart. Useful? A star helps.

Cérebro DeepSeek + transcrição automática de imagens: anexe imagens na GUI e cada uma é transcrita em texto por qualquer VLM compatível com OpenAI antes de chegar ao DeepSeek, que é somente texto — um caminho rápido com chave própria (padrão qwen3.7-flash; DashScope/Zhipu/OpenRouter ou qualquer endpoint compatível com OpenAI), ou Ollama local detectado automaticamente sem configuração.

Dsh-visual-plugin. Dê olhos ao seu modelo somente-texto: encaminhe imagens do usuário para qualquer modelo de visão compatível com OpenAI e veja os resultados em um painel à direita da Web UI

AI image generation for the DSH Web GUI: text-to-image and image-to-image through a configurable OpenAI-compatible endpoint (gpt-image-2 / gpt-image-1 / dall-e-3), with an api_url/api_key settings card and a sidebar split-pane generation studio.

On-demand vision for text-only DSH sessions: images become markers, and a vision_describe tool sends only image + question to an OpenAI-compatible vision model

NewAPI (OpenAI-compatible gateway) LLM provider: registers a `newapi` route with chat-only model discovery, auto-fills model parameters (context window, reasoning effort) from models.dev, and adds a Web settings section for the base URL and API key.

Cherry Studio-style knowledge base system for DeepSeek Harness (DSH): bases, documents, chunking, embeddings (OpenAI-compatible / Ollama / local / lexical fallback), retrieval, model-facing tools, and a browser management panel

Adiciona suporte a níveis de esforço de raciocínio baixo, médio, alto e outros às APIs de terceiros do DeepSeek Harness, permitindo escolher o modelo para cada chamada de subagente

Declaração de capacidades por modelo para o DeepSeek Harness: níveis de esforço de raciocínio (grafias de protocolo) + modalidades de requisição (visão) para providers compatíveis com OpenAI. Seção de configurações, zero dependências de runtime do harness, sem YAML.

O seletor de modelos para o DSH: aponte para qualquer endpoint compatível com OpenAI, com presets selecionados de provedores DeepSeek gratuitos/baratos e fallback automático quando um nível gratuito limita sua taxa

Imagens anexadas no compositor são transcritas para texto por um modelo de visão compatível com OpenAI antes de chegar aos modelos DeepSeek somente de texto

LoongPort DeepSeek Harness (dsh) Cordis bundle and setup CLI

DeepSeek Harness plugin: import models with capabilities from an OpenAI-compatible /v1/models listing (gateway capability extensions) and edit per-model capabilities (thinking, vision) on its settings page

Voice pair: free edge-tts neural speech synthesis + OpenAI-compatible ASR transcription.

Universal image generation for DeepSeek Harness: auto-discovers image models from any OpenAI-compatible endpoint (SenseNova, StepFun, Agnes, Qwen, Flux, SD, Imagen and more), with agent tools and REST API.

Renders pasted/uploaded images inline in the DSH Web chat and gives text-only models vision: the model-invokable visual_review tool calls any OpenAI-compatible multimodal API first, falling back to a local Qwen3-VL worker.

Full vision-capability bundle for DeepSeek Harness: a vision_understand tool (OpenAI-compatible vision APIs, free Zhipu GLM-4V-Flash by default) plus paste/drag-and-drop/button entry points for image recognition.

One-click ✨ polish button for the composer: rewrites prompts and drafts with WorkBuddy humanizer-style rules (kills AI-flavored phrasing, varies rhythm, mode-aware for instructions/questions/prose) via free Zhipu GLM-4.5-Flash or any OpenAI-compatible API, falling back to offline local rules.

让 DeepSeek Harness 里任何纯文本模型都能读图。识图是按需调用的 tool —— 图片不进主模型上下文，不看就不花钱；附 23 处缺陷的评测集，换模型可自测。

Multimodal plugin for DeepSeek Harness: understand images and generate images through configurable OpenAI-compatible or DashScope endpoints.

Dual-protocol DIT.ai provider bundle for DeepSeek Harness

DeepSeek Harness plugin: let text-only models receive pasted images, and analyze them with a built-in OpenAI-compatible vision tool

Speech-to-text voice input for the web UI: a mic button in the composer transcribes speech into the draft via the browser Web Speech API (zero-config) or an OpenAI-compatible Whisper API (OpenAI / Groq), with a selectable model and language in Settings.

Chat image-attachment bridge with a `view_image` tool for any OpenAI-compatible VLM (local Ollama or cloud): pasted/dropped images become `view_image` path markers before reaching text-only DeepSeek models.